Skip to main content

Security Audit

arc-sentinel

github.com/openclaw/skills
AI SkillCommit 13146e6a3d46
10
CRITICAL
Scanned about 2 months ago
5
Critical
Immediate action required
3
High
Priority fixes suggested
6
Medium
Best practices review
1
Low
Acknowledged / Tracked

Trust Assessment

arc-sentinel received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 15 findings: 5 critical, 3 high, 6 medium, and 1 low severity. Key findings include File read + network send exfiltration, Sensitive environment variable access: $HOME, Sensitive environment variable access: $AWS_CREDS.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 10/100, indicating areas for improvement.

Last analyzed on February 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis
10%
Static Code Analysis
13%
Dependency Graph
98%
LLM Behavioral Safety
40%

Behavioral Risk Signals

Network Access
4 findings
Filesystem Write
8 findings
Shell Execution
11 findings
Dynamic Code
2 findings
Excessive Permissions
13 findings

Security Findings15

SeverityFindingLayerLocation

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/0cc5e2b632a1c62c.svg)](https://skillshield.io/report/0cc5e2b632a1c62c)
SkillShield Badge

Powered by SkillShield